JP7626221B2 - Interpolation device, gait measurement system, interpolation method, and program - Google Patents

Description

The present disclosure relates to an interpolation device that interpolates missing time series data.

With growing interest in health care for managing physical condition, attention is being paid to services that measure the characteristics contained in walking patterns (also called gait) and provide users with information corresponding to their gait. For example, devices have been developed that analyze a user's gait by mounting a measurement device including an inertial sensor on footwear such as shoes. In such gait analysis, when data measured by a sensor (also called sensor data) is wirelessly transmitted from the measurement device, data loss can occur due to factors such as communication failure.

Patent Document 1 discloses a gait measurement system that aims to remove drift that shows different characteristics between the period when the foot is on the ground (stance phase) and the period when the foot is off the ground (swing phase). The system of Patent Document 1 detects at least one walking phase from acceleration data measured by an inertial measurement unit, and calculates velocity data by time-integrating the acceleration data. The system of Patent Document 1 calculates a correction amount corresponding to each walking phase based on the walking phase and the velocity data. The system of Patent Document 1 calculates corrected velocity data by subtracting the correction amount from the velocity data corresponding to each walking phase, and calculates trajectory data by time-integrating the calculated corrected velocity data.

Patent Document 2 discloses a signal interpolation method for interpolating missing portions of an input signal. In the method of Patent Document 2, the period of the signal before the input signal is missing is detected and the detected input signal is stored. In the method of Patent Document 2, the stored signal is read out in response to the detection of the input signal to interpolate the missing portion. In the method of Patent Document 2, the polarity and level at the start of the input signal missing are identified, and accumulated waveform signals of polarity and level that maintain continuity with the input signal immediately before the missing portion are sequentially read out. In the method of Patent Document 2, the level of the accumulated waveform signal is gradually made to approximate the level of the input signal, thereby interpolating the missing portion of the input signal so that continuity is maintained.

Patent Document 3 discloses a data interpolation device that interpolates missing data measured by sensors or devices connected to a network. The device of Patent Document 3 stores a time series model of data and an interpolation method for interpolating missing data. The interpolation method corresponds to a phase in the time series model that is specified as a range in which the time changes of data are common. The device of Patent Document 3 accumulates data output from an external device for each external device, and determines which time series model the time change pattern of the accumulated data corresponds to. The device of Patent Document 3 determines which phase of the determined time series model a missing part of the accumulated data is located in, and interpolates the missing part using an interpolation method according to the determined phase.

Patent document 4 discloses a bioinformation measuring device that complements missing parts contained in bioinformation. The device of Patent document 4 complements missing parts contained in time series data (biological information) measured by a pulse wave sensor and an electrocardiogram sensor. The device of Patent document 4 complements missing parts of data measured by one of the two sensors based on data measured by the other sensor. The device of Patent document 4 identifies a corresponding section of data before the start point of the missing part of the time series data measured by the other sensor, where an index indicating a correlation between the missing part and the time series data of the same time section satisfies a predetermined condition. The device of Patent document 4 complements the missing part using time series data of the same time section as the corresponding section of data measured by one sensor.

International Publication No. 2020/105115 Japanese Patent Application Laid-Open No. 61-227432 JP 2014-102779 A JP 2010-264168 A

The method of Patent Document 1 can remove drifts that show clearly different characteristics in different gait periods, such as the stance phase and swing phase. However, the method of Patent Document 1 cannot fill in missing parts that occur locally in individual gait periods, such as the stance phase and swing phase. Therefore, the method of Patent Document 1 cannot restore the features contained in the missing parts.

In the method of Patent Document 2, when there is a gap in the input signal, the accumulated signal is repeatedly read out to interpolate the missing portion so that continuity is obtained from the start of the gap to the end of the gap. According to the method of Patent Document 2, when the input signal has a simple periodicity or shape, the missing portion can be interpolated. However, with the method of Patent Document 2, when the input signal has a complex regularity or waveform, such as sensor data, it is difficult to interpolate the missing portion so that continuity is obtained from the start of the gap to the end of the gap. Therefore, with the method of Patent Document 2, there is a possibility that features contained in the missing portion may be lost.

In the method of Patent Document 3, it is necessary to store the time series model and the interpolation method in advance. Therefore, in the method of Patent Document 3, it is not possible to interpolate missing data for missing data for which the time series model or the interpolation method cannot be specified.

In the method of Patent Document 4, two related time series data measured at the same time are matched, and missing parts of one time series data are complemented based on the other data. Therefore, the method of Patent Document 4 cannot complement missing parts unless there is time series data measured at the same time.

The objective of the present disclosure is to provide an interpolation device, etc., capable of interpolating data in missing sections, including the characteristics of the missing sections of data contained in time series data of sensor data.

An interpolation device according to one aspect of the present disclosure includes a gait information processing unit that generates a walking waveform for each walking cycle using time-series data of sensor data relating to foot movement and identifies missing sections of data in the time-series data, a missing information processing unit that calculates the walking phase of the identified missing section, and an interpolation unit that generates interpolation data to interpolate the missing section using walking phase data of the missing section in a walking waveform of a walking cycle different from the walking cycle that includes the missing section, and interpolates the generated interpolation data into the missing section.

In one embodiment of the interpolation method disclosed herein, a computer generates a gait waveform for each gait cycle using time series data of sensor data related to foot movement, identifies missing sections of data in the time series data, calculates the gait phase of the identified missing section, generates interpolation data that interpolates the missing section using data on the gait phase of the missing section in a gait waveform of a gait cycle different from the gait cycle that includes the missing section, and interpolates the generated interpolation data into the missing section.

A program according to one embodiment of the present disclosure causes a computer to execute the following processes: generating a gait waveform for each gait cycle using time series data of sensor data relating to foot movement; identifying missing sections of data in the time series data; calculating the gait phase of the identified missing section; generating interpolation data that interpolates the missing section using data on the gait phase of the missing section in a gait waveform of a gait cycle different from the gait cycle that includes the missing section; and interpolating the generated interpolation data into the missing section.

According to the present disclosure, it is possible to provide an interpolation device, etc., that can interpolate data in missing sections, including the characteristics of the missing sections of data contained in time series data of sensor data.

1 is a block diagram showing an example of a configuration of a gait measurement system according to a first embodiment. FIG. FIG. 1 is a conceptual diagram showing an example of arrangement of measurement devices in a gait measurement system according to a first embodiment. FIG. 2 is a conceptual diagram for explaining an example of a coordinate system set in a measurement device of the gait measurement system according to the first embodiment. FIG. 1 is a conceptual diagram for explaining a walking cycle. FIG. 11 is a conceptual diagram for explaining a defect that occurs in time-series data of sensor data. FIG. 11 is a conceptual diagram for explaining an example of interpolating missing data that occurs in time-series data of sensor data using an analytical method. 4 is a conceptual diagram for explaining interpolation of a missing section by the interpolation device of the gait measurement system according to the first embodiment. FIG. 1 is a block diagram showing an example of the configuration of a measurement device of a gait measurement system according to a first embodiment. FIG. 1 is a block diagram showing an example of a configuration of an interpolation device of a gait measurement system according to a first embodiment. FIG. FIG. 2 is a conceptual diagram showing an example of interpolation of a defect by the interpolation device of the gait measurement system according to the first embodiment. 4 is a conceptual diagram for explaining interpolation of a defect by the interpolation device of the gait measurement system according to the first embodiment. FIG. 1 is a block diagram showing an example of a configuration of a gait measurement device of a gait measurement system according to a first embodiment. FIG. 5 is a flowchart for illustrating an example of the operation of a gait information processing unit included in the interpolation device of the gait measurement system according to the first embodiment. 10 is a flowchart for illustrating an example of the operation of a missing information processing unit included in the interpolation device of the gait measurement system according to the first embodiment. 5 is a flowchart for illustrating an example of the operation of an interpolation unit included in the interpolation device of the gait measurement system according to the first embodiment. 10 is a flowchart for illustrating another example of the operation of the interpolation unit included in the interpolation device of the gait measurement system according to the first embodiment. FIG. 11 is a block diagram showing an example of a configuration of a gait measurement system according to a second embodiment. FIG. 13 is a block diagram showing an example of the configuration of an interpolation device of a gait measurement system according to a second embodiment. 1 is an example of time-series data of sensor data spanning a plurality of walking cycles. 13 is an example of a gait waveform obtained by normalizing time series data for one walking cycle, extracted from time series data of sensor data spanning a plurality of walking cycles. 13 shows a frequency distribution of data values in walking phase P1 and walking phase P2, with walking waveforms of multiple walking cycles forming a sample group (whole). 13 is a graph showing the correlation of standard deviations in the overall distribution of data values of data N and data N+1 of consecutive walking phases. 13 is a graph showing the correlation coefficient of the deviation value according to the distance from a target walking phase. 10 is a graph for explaining the interpolation of a missing section by an interpolation device according to a second embodiment; 10 is a flowchart illustrating an operation of the interpolation device according to the second embodiment. FIG. 13 is a block diagram showing an example of a configuration of an interpolation device according to a third embodiment. FIG. 2 is a block diagram showing an example of a hardware configuration for executing control and processing according to each embodiment.

Below, the form for implementing the present invention is explained using the drawings. However, the embodiment described below has technically preferable limitations for implementing the present invention, but does not limit the scope of the invention to the following. In addition, in all the drawings used to explain the following embodiments, the same symbols are used for similar parts unless there is a special reason. Also, in the following embodiments, repeated explanations of similar configurations and operations may be omitted.

(First embodiment)
First, a gait measurement system according to a first embodiment will be described with reference to the drawings. The gait measurement system of this embodiment measures physical quantities (sensor data) related to foot movement by a measurement device installed in footwear worn by a user. The measurement device includes an acceleration sensor and an angular velocity sensor. For example, the physical quantities related to foot movement include acceleration in three axial directions (also called spatial acceleration) measured by an acceleration sensor and angular velocity around three axes (also called spatial angular velocity) measured by an angular velocity sensor. The gait measurement system of this embodiment interpolates missing parts of data that occur during communication of measured sensor data, etc.

(composition)
1 is a block diagram showing the configuration of a gait measurement system 1 according to this embodiment. The gait measurement system 1 includes a measurement device 11, an interpolation device 12, and a gait measurement device 13. The interpolation device 12 may be connected to the measurement device 11 and the gait measurement device 13 by wire or wirelessly. The measurement device 11, the interpolation device 12, and the gait measurement device 13 may be configured as a single device. The gait measurement system 1 may be configured from the interpolation device 12 and the gait measurement device 13, excluding the measurement device 11.

The measuring device 11 is installed on the foot. For example, the measuring device 11 is installed on footwear such as shoes. For example, the measuring device 11 is placed at the back of the arch of the foot. The measuring device 11 includes an acceleration sensor and an angular velocity sensor. The measuring device 11 measures the acceleration (also called spatial acceleration) measured by the acceleration sensor and the angular velocity (also called spatial angular velocity) measured by the angular velocity sensor as physical quantities related to the movement of the foot of the user wearing the footwear. The physical quantities related to the movement of the foot measured by the measuring device 11 also include the velocity, angle, and position (trajectory) calculated by integrating the acceleration and angular velocity. The measuring device 11 converts the measured physical quantities into digital data (also called sensor data). The measuring device 11 transmits the converted sensor data to the interpolation device 12. The sensor data includes a timestamp corresponding to the time when the sensor data was acquired. The timestamp is a time series number assigned to the sensor data. For example, the measuring device 11 is connected to the interpolation device 12 via a mobile terminal (not shown) carried by the user.

The mobile terminal (not shown) is a communication device that can be carried by a user. For example, the mobile terminal is a portable communication device with communication functions such as a smartphone, a smart watch, or a mobile phone. The mobile terminal receives sensor data related to the movement of the user's feet from the measurement device 11. The mobile terminal transmits the received sensor data to a server or cloud in which the interpolation device 12 is implemented. Note that the functions of the interpolation device 12 and the gait measurement device 13 may be realized by application software or the like installed on the mobile terminal. In that case, the mobile terminal processes the received sensor data using application software or the like installed on the mobile terminal.

The measurement device 11 is realized, for example, by an inertial measurement device including an acceleration sensor and an angular velocity sensor. An example of an inertial measurement device is an IMU (Inertial Measurement Unit). The IMU includes an acceleration sensor that measures acceleration in three axial directions and an angular velocity sensor that measures angular velocity around three axes. The measurement device 11 may also be realized by an inertial measurement device such as a VG (Vertical Gyro) or an AHRS (Attitude Heading). The measurement device 11 may also be realized by a GPS/INS (Global Positioning System/Inertial Navigation System).

2 is a conceptual diagram showing an example of the arrangement of the measuring device 11 in the shoe 100. In the example of FIG. 2, the measuring device 11 is arranged at a position that hits the back side of the arch of the foot. For example, the measuring device 11 is arranged in an insole inserted into the shoe 100. For example, the measuring device 11 is arranged on the bottom surface of the shoe 100. For example, the measuring device 11 may be embedded in the body of the shoe 100. The measuring device 11 may be detachable from the shoe 100, or may not be detachable from the shoe 100. Note that the measuring device 11 may be arranged at a position other than the back side of the arch of the foot, as long as it can acquire sensor data related to the movement of the foot. The measuring device 11 may also be installed in socks worn by the user or in an accessory such as an anklet worn by the user. The measuring device 11 may also be attached directly to the foot or embedded in the foot. FIG. 2 shows an example in which the measuring device 11 is arranged in the shoe 100 on the right foot side, but the measuring device 11 may be arranged in the shoes 100 for both feet. If the measuring device 11 is placed in the shoes 100 for both feet, the gait can be measured based on the movements of both feet.

3 is a conceptual diagram for explaining the local coordinate system (x-axis, y-axis, z-axis) set in the measuring device 11 when the measuring device 11 is placed on the back side of the arch of the foot, and the world coordinate system (x-axis, y-axis, z-axis) set with respect to the ground. In the world coordinate system (x-axis, y-axis, z-axis), when the user is standing upright, the user's lateral direction is set to the x-axis direction (rightward is positive), the direction in front of the user (direction of travel) is set to the y-axis direction (forward is positive), and the direction of gravity is set to the z-axis direction (vertically upward is positive). In this embodiment, a local coordinate system consisting of the x-direction, y-direction, and z-direction is set with the measuring device 11 as the reference.

Figure 4 is a conceptual diagram for explaining a step cycle based on the right foot. Figure 4 shows one walking cycle of the right foot, starting from the time when the heel of the right foot lands on the ground and ending from the time when the heel of the right foot lands on the ground. Figure 4 shows a walking cycle normalized by setting one walking cycle of the right foot as 100%. One walking cycle of one foot is roughly divided into a stance phase in which at least a part of the sole of the foot is in contact with the ground, and a swing phase in which the sole of the foot is off the ground. In this embodiment, the walking cycle is normalized so that the stance phase accounts for 60% and the swing phase accounts for 40%. The stance phase is further divided into an early stance phase T1, a mid stance phase T2, a final stance phase T3, and a pre-swing phase T4. The swing phase is further divided into an early swing phase T5, a mid swing phase T6, and a final swing phase T7. The walking waveform for one step cycle does not have to start from the time when the heel hits the ground. For example, the walking waveform for one step cycle may start and end from the time when the heel lifts off the ground.

Figure 4(a) shows an event where the heel of the right foot touches the ground (heel strike) (HS: Heel Strike). Figure 4(b) shows an event where the toe of the left foot leaves the ground (opposite toe off) while the sole of the right foot is in contact with the ground (OTO: Opposite Toe Off). Figure 4(c) shows an event where the heel of the right foot rises (heel rise) while the sole of the right foot is in contact with the ground (HR: Heel Rise). Figure 4(d) shows an event where the heel of the left foot touches the ground (opposite heel strike) (OHS: Opposite Heel Strike). Figure 4(e) shows an event where the toe of the right foot leaves the ground (toe off) while the sole of the left foot is in contact with the ground (TO: Toe Off). Fig. 4(f) shows an event where the left and right feet cross (foot crossing) with the sole of the left foot touching the ground (FA: Foot Adjacent). Fig. 4(g) shows an event where the tibia of the right foot is almost perpendicular to the ground (TV: Tibia Vertical) with the sole of the left foot touching the ground. Fig. 4(h) shows an event where the heel of the right foot touches the ground (heel strike) (HS: Heel Strike). Fig. 4(h) corresponds to the end point of the walking cycle that starts from Fig. 4(a) and corresponds to the starting point of the next walking cycle.

The initial stance phase T1 is the period from heel-on-striking HS to toe-off OTO. The mid-stance phase T2 is the period from toe-off OTO to heel-lift HR. The final stance phase T3 is the period from heel-lift HR to heel-on-striking OHS. The early swing phase T4 is the period from heel-on-striking OHS to toe-off TO. The initial swing phase T5 is the period from toe-off TO to foot crossing FA. The mid-striking phase T6 is the period from foot crossing FA to tibia vertical TV. The final swing phase T7 is the period from tibia vertical TV to heel-on-striking HS. The timing at which walking events occur varies depending on the person, physical condition, and walking state, and does not necessarily match the expected walking cycle.

In walking, periodic movements are repeated as shown in FIG. 4. Therefore, the skeleton and muscles used at the same timing (also called walking phase) in different walking cycles are almost the same. Therefore, the waveforms of the time series data of the sensor data measured during walking are similar in each walking phase. In this embodiment, missing sections of the time series data of the walking cycle to be interpolated are interpolated using data without missing parts contained in the time series data of a walking cycle different from the walking cycle to be interpolated.

The interpolation device 12 receives sensor data from the measurement device 11. The interpolation device 12 generates time series data of the received sensor data. The interpolation device 12 generates the time series data based on the timestamps included in the sensor data. The interpolation device 12 extracts a waveform for one step walking cycle from the generated time series data. For example, the interpolation device 12 extracts a waveform for one step walking cycle starting from the timing of heel strike or heel lift. The interpolation device 12 normalizes the extracted waveform for one step walking cycle to generate a waveform for one step walking cycle (also called a walking waveform).

The interpolation device 12 identifies a portion of the time series data of the sensor data where a time stamp number is missing as a missing section. The interpolation device 12 generates interpolation data for interpolating data of the missing section using a walking waveform in another walking cycle that is free of missing data in the same walking phase as the missing section. The interpolation device 12 uses the generated interpolation data to interpolate the missing section.

Figure 5 is a conceptual diagram for comparing a normal waveform with a waveform that includes missing parts (also called a missing waveform). Figure 5 is a walking waveform of forward acceleration (Y-direction acceleration) in a step cycle starting from heel lift. The missing waveform in Figure 5 includes two missing sections. As shown in Figure 5, the data in the missing sections may include gait characteristics.

FIG. 6 is a conceptual diagram for explaining an example of interpolation of missing sections of time series data in the related art. FIG. 6 shows an example of interpolating data of missing sections by an analytical method with reference to the time stamps of sensor data included in the time series data. FIG. 6 shows linear interpolation (dashed line) that connects the start point and end point of the missing section with a line segment (linear function) and polynomial interpolation (dash-dotted line) that connects the start point and end point of the missing section with a curve. In linear interpolation, the start point and end point of the missing section are connected with a line segment. In linear interpolation, the unevenness of the amplitude appearing in the time series data cannot be restored, and therefore the characteristics of the section including the unevenness cannot be restored. In polynomial interpolation, the start point and end point of the missing section are connected with a curve. In polynomial interpolation, the unevenness of the time series data can be roughly restored, but the fine features included in the unevenness cannot be restored.

Figure 7 is a conceptual diagram for explaining an example of restoration of missing sections of time series data in this embodiment. In the example of Figure 7, data of missing sections S1 to S5 contained in each of the walking waveforms of walking cycles i to i+3 are mutually interpolated (i is a natural number). The walking waveform of walking cycle i includes missing sections S1 and S5. The walking waveform of walking cycle i+1 includes missing sections S2 and S3. The walking waveform of walking cycle i+2 includes missing section S4. The walking waveform of walking cycle i+3 does not include any missing sections.

The interpolation device 12 uses data of the walking phase corresponding to the missing section S1 included in the walking waveform of the walking cycle i+1 to 3 to interpolate the missing section S1 included in the walking waveform of the walking cycle i. The interpolation device 12 uses data of the walking phase corresponding to the missing section S5 included in the walking waveform of the walking cycle i+1 to 3 to interpolate the missing section S5 included in the walking waveform of the walking cycle i. The interpolation device 12 interpolates the missing section S2 included in the walking waveform of the walking cycle i+1 with data of the walking phase corresponding to the missing section S2 included in the walking waveform of the walking cycle i, i+2 to 3. The interpolation device 12 interpolates the missing section S3 included in the walking waveform of the walking cycle i+1 with data of the walking phase corresponding to the missing section S3 included in the walking waveform of the walking cycle i, i+2 to 3. The interpolation device 12 interpolates the missing section S4 included in the walking waveform of the walking cycle i+2 with data of the walking phase corresponding to the missing section S4 included in the walking waveform of the walking cycle i to i+1, i+3.

For example, for a missing section of time series data that occurs in certain time series data, the interpolation device 12 selects at least one piece of walking phase data corresponding to the missing section from at least one walking waveform that does not have missing data for the missing section. For example, the interpolation device 12 uses the selected data to generate interpolation data for interpolating the missing section.

For example, for a missing section of time series data occurring in certain time series data, the interpolation device 12 selects multiple pieces of walking phase data corresponding to the missing section from multiple walking waveforms in which data for the missing section is not missing. The interpolation device 12 calculates an average value, such as an arithmetic average or a weighted average, for the multiple selected pieces of data, and generates interpolation data for interpolating the missing section using the calculated average value. For example, the interpolation device 12 generates interpolation data using the data among the multiple selected pieces of data that has the closest values for the start point and end point of the missing section.

For example, the interpolation device 12 may select a method for interpolating data of a missing section depending on the walking period of the missing section. For example, the waveform of the acceleration in the direction of travel (Y-direction acceleration) fluctuates little during the stance phase and fluctuates greatly during the swing phase. Therefore, the interpolation device 12 may be configured to interpolate data of a missing section occurring during the stance phase using an analytical method, and to interpolate data of a missing section occurring during the swing phase based on the walking waveform of another walking cycle.

For example, the interpolation device 12 is implemented in a server or the like (not shown). For example, the interpolation device 12 may be realized by an application server. For example, the interpolation device 12 may be realized by application software or the like installed on a mobile terminal (not shown).

The gait measurement device 13 acquires a gait waveform that does not include a missing section from the interpolation device 12. The gait measurement device 13 uses the acquired gait waveform to perform measurements related to gait. For example, the gait measurement device 13 detects a gait event from the gait waveform and measures the user's gait based on the detected gait event. For example, the gait measurement device 13 measures gait such as stride length, step length, stride width, foot angle, and walking speed based on the detected gait event. For example, the gait measurement device 13 may estimate physical conditions such as the degree of pronation/supination, the progression of hallux valgus, body symmetry, and body flexibility based on the measured gait. For example, the gait measurement device 13 may measure physical parameters such as the length of the upper limbs, lower limbs, upper arms, forearms, upper legs, and lower legs based on the measured gait. There are no particular limitations on the items to be measured by the gait measurement device 13.

The gait measurement device 13 outputs measurement results related to gait (also referred to as gait information). For example, the gait measurement device 13 outputs the gait information to a display device (not shown) or a mobile terminal (not shown). The gait information output to the display device is displayed on the screen of the display device or the mobile terminal. For example, the gait measurement device 13 outputs the gait information to an external system (not shown). The gait information output from the gait measurement device 13 can be used for any purpose. There are no particular limitations on the communication function through which the gait measurement device 13 outputs the gait information.

For example, the gait measurement device 13 is implemented in a server or the like (not shown). For example, the gait measurement device 13 may be realized by an application server. For example, the gait measurement device 13 may be realized by application software or the like installed on a mobile terminal (not shown).

[Measuring equipment]
Next, a detailed configuration of the measurement device 11 will be described with reference to the drawings. Fig. 8 is a block diagram showing an example of a detailed configuration of the measurement device 11. The measurement device 11 has an acceleration sensor 111, an angular velocity sensor 112, a control unit 113, and a transmission unit 115. The measurement device 11 also includes a power supply (not shown).

The acceleration sensor 111 is a sensor that measures acceleration in three axial directions (also called spatial acceleration). The acceleration sensor 111 outputs the measured acceleration to the control unit 113. For example, a piezoelectric type, a piezo-resistive type, a capacitance type, or other type of sensor can be used for the acceleration sensor 111. Note that there are no limitations on the measurement method of the sensor used for the acceleration sensor 111 as long as it can measure acceleration.

Angular velocity sensor 112 is a sensor that measures angular velocity (also called spatial angular velocity) in three axial directions. Angular velocity sensor 112 outputs the measured angular velocity to control unit 113. For example, a vibration type, a capacitance type, or other type of sensor can be used for angular velocity sensor 112. Note that there are no limitations on the measurement method of the sensor used for angular velocity sensor 112 as long as it can measure angular velocity.

The control unit 113 acquires the acceleration in three axial directions and the angular velocity around the three axes from each of the acceleration sensor 111 and the angular velocity sensor 112. The control unit 113 converts the acquired acceleration and angular velocity into digital data and outputs the converted digital data (also called sensor data) to the transmission unit 115. The sensor data includes at least the acceleration data converted into digital data and the angular velocity data converted into digital data. The acceleration data includes an acceleration vector in the three axial directions. The angular velocity data includes an angular velocity vector around the three axes. The acceleration data and the angular velocity data are linked to the acquisition time of the data. The control unit 113 may also be configured to output sensor data that has been corrected for mounting errors, temperature correction, linearity correction, and the like, for the acquired acceleration data and angular velocity data. The control unit 113 may also generate angle data around the three axes using the acquired acceleration data and angular velocity data.

For example, the control unit 113 is a microcomputer or microcontroller that performs overall control of the measuring device 11 and data processing. For example, the control unit 113 has a CPU (Central Processing Unit), a RAM (Random Access Memory), a ROM (Read Only Memory), a flash memory, etc. The control unit 113 controls the acceleration sensor 111 and the angular velocity sensor 112 to measure angular velocity and acceleration. For example, the control unit 113 performs AD conversion (Analog-to-Digital Conversion) of physical quantities (analog data) such as the measured angular velocity and acceleration. The control unit 113 stores the converted digital data in a storage unit (not shown) such as a flash memory. Note that the physical quantities (analog data) measured by the acceleration sensor 111 and the angular velocity sensor 112 may be converted to digital data in each of the acceleration sensor 111 and the angular velocity sensor 112. The digital data stored in the storage unit is output to the transmission unit 115 at a predetermined timing.

The transmitting unit 115 acquires sensor data from the control unit 113. The transmitting unit 115 transmits the acquired sensor data to the interpolation device 12. For example, the transmitting unit 115 transmits the sensor data to the interpolation device 12 via a wired connection such as a cable. For example, the transmitting unit 115 transmits the sensor data to the interpolation device 12 via wireless communication. For example, the transmitting unit 115 is configured to transmit the sensor data to the interpolation device 12 via a wireless communication function (not shown) conforming to a standard such as Bluetooth (registered trademark) or WiFi (registered trademark). Note that the communication function of the transmitting unit 115 may be conforming to a standard other than Bluetooth (registered trademark) or WiFi (registered trademark).

[Interpolation device]
Next, a detailed configuration of the interpolation device 12 will be described with reference to the drawings. Fig. 9 is a block diagram for explaining the detailed configuration of the interpolation device 12. The interpolation device 12 has a receiving unit 121, a gait information processing unit 122, a missing information processing unit 123, a storage unit 125, an interpolation unit 126, and a transmitting unit 128.

The receiving unit 121 receives sensor data from the measuring device 11. The receiving unit 121 outputs the received sensor data to the gait information processing unit 122. For example, the receiving unit 121 receives the sensor data from the measuring device 11 via a wired connection such as a cable. For example, the receiving unit 121 receives the sensor data from the measuring device 11 via wireless communication. For example, the receiving unit 121 is configured to receive the sensor data from the measuring device 11 via a wireless communication function (not shown) that complies with standards such as Bluetooth (registered trademark) or WiFi (registered trademark). Note that the communication function of the receiving unit 121 may be in accordance with standards other than Bluetooth (registered trademark) or WiFi (registered trademark).

The gait information processing unit 122 acquires sensor data measured in association with the walking of a user wearing the shoe 100 in which the measuring device 11 is installed from the receiving unit 121. The gait information processing unit 122 generates time-series data of the acquired sensor data based on the timestamp included in the sensor data. For example, the gait information processing unit 122 converts the coordinate system of the acquired sensor data from the local coordinate system to the world coordinate system.

The gait information processing unit 122 uses the sensor data to generate time series data of physical quantities related to foot movement. For example, the gait information processing unit 122 generates time series data such as spatial acceleration and spatial angular velocity. The gait information processing unit 122 also integrates the spatial acceleration and spatial angular velocity to generate time series data such as spatial velocity, spatial angle (sole angle), and spatial trajectory. These time series data correspond to the walking waveform. The gait information processing unit 122 generates time series data at a predetermined timing or time interval set according to a general walking cycle or a walking cycle specific to the user. The timing at which the gait information processing unit 122 generates the time series data can be set arbitrarily. For example, the gait information processing unit 122 is configured to continue generating time series data during the period during which the user continues walking. The gait information processing unit 122 may also be configured to generate time series data at a specific timing.

The gait information processing unit 122 extracts a waveform for one gait cycle from the generated time series data. For example, the gait information processing unit 122 extracts a waveform for one gait cycle starting from heel strike. For example, the gait information processing unit 122 detects the timing of heel strike in a gait waveform of forward acceleration (Y-direction acceleration) for one gait cycle. In a gait waveform of forward acceleration for one gait cycle, the timing of heel strike is the midpoint between the timing at which the minimum peak is detected and the timing at which the maximum peak that appears after the minimum peak is detected. For example, the gait information processing unit 122 extracts time series data starting from the timing of the preceding heel strike and ending at the timing of the succeeding heel strike as a waveform for one gait cycle starting from heel strike.

For example, the gait information processing unit 122 detects the timing of toe-off in the walking waveform of the forward acceleration for one walking cycle. In the walking waveform of the forward acceleration for one walking cycle, the timing of toe-off is the timing of a valley that appears between two peaks included in the maximum peak. For example, the gait information processing unit 122 detects the timing of toe-off in the walking waveform of the forward acceleration for one walking cycle as the timing of toe-off.

For example, the gait information processing unit 122 may extract a waveform for one step cycle starting from a heel lift. In the gait waveform of the plantar angle, a state in which the toe is located above the heel (dorsiflexion) is defined as negative, and a state in which the toe is located below the heel (plantar flexion) is defined as positive. The time at which the gait waveform of the plantar angle becomes minimum corresponds to the timing of the start of the stance phase. The time at which the gait waveform of the plantar angle becomes maximum corresponds to the timing of the start of the swing phase. The time at the midpoint between the start of the stance phase and the start of the swing phase corresponds to the timing of the center of the stance phase. The timing of the center of the stance phase corresponds to the timing of the heel lift. For example, the gait information processing unit 122 extracts time series data of two heel lifts included in the time series data for two steps, starting from the earlier timing and ending from the later timing. The extracted time series data is a gait waveform for one stride cycle starting from heel lift.

The gait information processing unit 122 normalizes the waveform of the extracted step cycle to generate a waveform of the step cycle (also called a walking waveform). The gait information processing unit 122 normalizes the time axis of the waveform of the step cycle to a walking cycle whose starting point timing is 0 and whose ending point timing is 100. The walking cycle of the normalized waveform is divided into 100 equal parts and expressed as a percentage. Each percentage of the walking cycle is called a walking phase. For example, the gait information processing unit 122 normalizes the walking cycle of the walking waveform so that the ratio of the stance phase to the swing phase is 60:40. For example, the gait information processing unit 122 may normalize the walking waveform based on walking events that appear in the walking waveform. For example, the gait information processing unit 122 normalizes the walking waveform with respect to the walking waveform starting from the timing of heel lift so that the timing of toe off is 30% and the timing of heel contact is 70%. Note that the timing at which a walking event occurs varies depending on the person, their physical condition, and their walking state, and therefore does not necessarily match perfectly with the expected walking phase.

The gait information processing unit 122 may also normalize the amplitude (acceleration or angular velocity value) of the walking waveform for one step gait cycle. For example, the gait information processing unit 122 normalizes the amplitude of the walking waveform for one step gait cycle so that the amplitude fluctuation range is within a certain range. For example, the gait information processing unit 122 normalizes the amplitude of the walking waveform for one step gait cycle so that the maximum amplitude value is 1 and the maximum amplitude value is -1. If the amplitude of the walking waveform is normalized, the amplitudes of the walking waveform for multiple gait cycles are aligned, making it easier to interpolate data in missing sections. The gait information processing unit 122 may also normalize the baseline of the walking waveform for one step gait cycle. For example, the gait information processing unit 122 normalizes the walking waveform for one step gait cycle so that the slope of the baseline is 0. If the baseline of the walking waveform is normalized, the slope of the baseline of the walking waveform for multiple gait cycles is aligned. Therefore, if the baseline of the walking waveform is normalized, it becomes easier to interpolate data in missing sections.

The gait information processing unit 122 stores the normalized walking waveform in the storage unit 125. For example, the gait information processing unit 122 stores only the walking waveform without a missing section in the storage unit 125. In that case, the missing information processing unit 123 may identify the missing section and then store the walking waveform with a missing section (also called a missing waveform) in the storage unit 125. For example, all walking waveforms including the missing waveform may be stored in the storage unit 125. In that case, the missing information processing unit 123 may acquire the missing waveform stored in the storage unit 125 and identify the missing section included in the missing waveform. The data of the missing section of the walking waveform stored in the storage unit 125 (also called normal data) is used to interpolate the missing section included in the missing waveform.

The missing information processing unit 123 acquires the missing waveform. The missing information processing unit 123 may acquire the missing waveform from the gait information processing unit 122, or may acquire the missing waveform from the memory unit 125. The missing information processing unit 123 identifies a portion of the acquired missing waveform where a timestamp number is missing as a missing section. For example, the missing information processing unit 123 determines which data is missing from the start point of the missing section in the walking waveform of a step cycle, and calculates the missing walking phase. For example, the missing information processing unit 123 may identify the walking period of the missing section based on the timestamp number.

The missing information processing unit 123 stores information about the missing section included in the missing waveform (also called missing information) in the storage unit 125 in association with the missing waveform. For example, the missing information processing unit 123 stores the walking phases at the start and end of the missing section in association with the missing waveform as missing information in the storage unit 125. For example, the missing information processing unit 123 may store the walking phases at the start and end of the missing section and the amplitude value at the walking phase in association with the missing waveform as missing information in the storage unit 125. The missing information processing unit 123 may also be configured to output the missing information to the interpolation unit 126.

A walking waveform is stored in the memory unit 125. A walking waveform that does not include a missing section (also called a normal waveform) is stored in the memory unit 125. In addition, a walking waveform that includes a missing section (also called a missing waveform) and a walking waveform in which a missing section has been repaired (also called a repaired waveform) are stored in the memory unit 125. A missing waveform is the subject of interpolation of the missing section. Missing information of the missing waveform is associated with the missing waveform. The normal waveform and the repaired waveform are used for gait measurement by the gait measurement device 13. The walking waveform stored in the memory unit 125 is acquired by the transmission unit 128 at a predetermined timing and transmitted from the transmission unit 128 to the gait measurement device 13.

The interpolation unit 126 acquires a missing waveform. The interpolation unit 126 acquires a missing waveform from the memory unit 125 or the missing information processing unit 123. The missing waveform acquired by the interpolation unit 126 includes information (missing information) on the missing section identified by the missing information processing unit 123. The interpolation unit 126 uses data of a walking waveform with a walking cycle different from the acquired missing waveform to interpolate the missing section included in the missing waveform. The interpolation unit 126 extracts normal data in the walking phase corresponding to the missing section from the walking waveform with a walking cycle different from the missing waveform. The interpolation unit 126 generates interpolation data for interpolating the missing section using the extracted interpolation data.

For example, the missing waveform includes a missing section in the section where the walking phase is 10-20%. In this case, the interpolation unit 126 selects at least one walking waveform that does not include a missing section in the section where the walking phase is 10-20% from among the walking waveforms stored in the memory unit 125. The interpolation unit 126 extracts normal data for the section where the walking phase is 10-20% from the at least one selected walking waveform. For example, for a missing section included in a certain missing waveform, the interpolation unit 126 selects at least one normal data for the walking phase corresponding to the missing section from at least one walking waveform that is not missing data for the missing section. The interpolation unit 126 generates interpolation data for interpolating the missing section using the selected normal data.

For example, for a missing section included in a certain missing waveform, the interpolation unit 126 selects multiple pieces of data for the walking phase corresponding to the missing section from multiple walking waveforms in which data for the missing section is not missing. For example, the interpolation unit 126 calculates interpolation data for each individual walking phase included in the missing section. The interpolation unit 126 calculates an average value, such as an arithmetic average or a weighted average, for the multiple selected pieces of data, and generates interpolation data for interpolating the missing section using the calculated average value. For example, the interpolation unit 126 generates interpolation data using data, of the multiple selected pieces of data, that has values for the start point and end point of the missing section that are closest to each other.

For example, the interpolation unit 126 may select a method for interpolating data of a missing section according to the walking period of the missing section. For example, the waveform of the acceleration in the direction of travel (Y-direction acceleration) fluctuates less during the stance phase and fluctuates more during the swing phase. That is, the swing phase (also called the first walking period) has more drastic data fluctuations than the stance phase (also called the second walking period), making it difficult to analytically interpolate data. In other words, the stance phase (second walking period) has less data fluctuations than the swing phase (first walking period), making it possible to analytically interpolate data. Therefore, the interpolation unit 126 may use an analytical method to interpolate the missing section included in the stance phase (second walking period). Then, the missing section included in the swing phase (first walking period) may be interpolated based on the walking waveform of another walking cycle. Note that the interpolation unit 126 may also perform analytical interpolation for a missing section included in the swing phase (first walking period) if the section has small fluctuations.

Figure 10 is a conceptual diagram for explaining the interpolation of missing sections in analytically interpolated sections. In the example of Figure 10, the amplitude fluctuation is small in the section where the walking phase is 0-20% and the section where the walking phase is 80%-100%. In contrast, the amplitude fluctuation is large in the section where the walking phase is 20-80%. In such a case, the interpolation unit 126 may perform analytical interpolation for the section where the walking phase is 0-20% and the section where the walking phase is 80%-100%. Since the amplitude fluctuation is large in the section where the walking phase is 20-80%, it is better for the interpolation unit 126 to generate interpolated data using data of other walking waveforms.

The interpolation unit 126 uses the generated interpolation data to interpolate the missing sections included in the missing waveform. For example, the interpolation unit 126 interpolates the missing waveform by inserting the interpolation data into the missing sections. For example, the interpolation unit 126 sequentially interpolates the missing sections with normal data included in the interpolation data from the start point of the missing section to the end point of the missing section. For example, the interpolation unit 126 may sequentially interpolate the missing sections with normal data included in the interpolation data from the end point of the missing section to the start point of the missing section. For example, the interpolation unit 126 may sequentially interpolate the normal data included in the interpolation data from the end point and the start point of the missing section.

For example, the interpolation unit 126 inserts a waveform formed by the interpolation data into the missing section. For example, the interpolation unit 126 inserts a waveform formed by the interpolation data so that the start point and the end point of the interpolation data match the start point and the end point of the missing section. For example, it is assumed that the start point and the end point of the interpolation data do not match the start point and the end point of the missing section. In such a case, the interpolation unit 126 rotates the baseline of the interpolation data so that the start point and the end point of the interpolation data match the start point and the end point of the missing section, and inserts the interpolation data into the missing section. For example, the interpolation unit 126 calculates the amplitude of the start point and the end point of the missing section based on the normal waveform of another walking cycle. For example, the interpolation unit 126 adjusts the baseline according to the difference between the calculated amplitude of the start point and the end point of the missing section and the actual amplitude of the start point and the end point of the missing section.

Figure 11 is a conceptual diagram showing an example of inserting a waveform composed of interpolated data into a missing section. (1) The interpolation unit 126 generates interpolated data for the missing section included in the missing waveform. (2) The interpolation unit 126 inserts the generated interpolated data into the missing section of the missing waveform. (3) The interpolation unit 126 sets a baseline for the interpolated data inserted into the missing section of the missing waveform. (4) The interpolation unit 126 rotates the baseline of the interpolated data inserted into the missing section of the missing waveform, and performs start-end point correction so that the start and end points of the missing section match the start and end points of the interpolated data, respectively.

The interpolation unit 126 stores the walking waveform (repaired waveform) in which the missing section has been interpolated in the storage unit 125. For example, the interpolation unit 126 may label the walking phase included in the missing section in the repaired waveform so that the repaired missing section can be identified. For example, the interpolation unit 126 may store the repaired waveform (also called the provisional repaired waveform) in which provisional interpolation data has been inserted in the missing section in the storage unit 125. For example, the gait measurement device 13 may correct the interpolation data inserted in the missing section included in the provisional repaired waveform. The repaired waveform stored in the storage unit 125 is used for gait measurement by the gait measurement device 13 in the same way as other walking waveforms that do not include a loss.

The transmission unit 128 acquires a gait waveform from the memory unit 125. The transmission unit 128 acquires a gait waveform including a normal waveform and a restored waveform from the memory unit 125. The transmission unit 128 transmits the acquired gait waveform to the gait measurement device 13. For example, the transmission unit 128 transmits the gait waveform to the gait measurement device 13 via a wire such as a cable. For example, the transmission unit 128 transmits the gait waveform to the gait measurement device 13 via wireless communication. There are no particular limitations on the communication method between the transmission unit 128 and the gait measurement device 13.

[Gait measurement device]
Next, a detailed configuration of gait measurement device 13 provided in gait measurement system 1 will be described with reference to the drawings. Fig. 12 is a block diagram showing an example of a detailed configuration of gait measurement device 13. Gait measurement device 13 has an acquisition unit 131, a detection unit 132, and a gait measurement unit 133. In reality, an output unit (communication interface) that outputs the estimation result by gait measurement unit 133 is provided, but in Fig. 12, the function of the output unit is included in gait measurement unit 133.

The acquisition unit 131 acquires a walking waveform from the interpolation device 12. The acquisition unit 131 acquires a walking waveform including a normal waveform and a restored waveform from the interpolation device 12. The acquisition unit 131 outputs the acquired walking waveform to the detection unit 132. For example, the acquisition unit 131 receives the walking waveform from the interpolation device 12 via a wire such as a cable. For example, the acquisition unit 131 receives the walking waveform from the interpolation device 12 via wireless communication. There are no particular limitations on the communication method between the interpolation device 12 and the acquisition unit 131.

The detection unit 132 acquires a walking waveform from the acquisition unit 131. The detection unit 132 detects walking periods and walking events from the acquired walking waveform. For example, the detection unit 132 detects walking periods such as a stance phase and a swing phase from the walking waveform. For example, the detection unit 132 detects walking events such as heel strike, opposite foot toe off, heel lift, opposite foot heel strike, toe off, foot crossing, and tibia vertical from the walking waveform. For example, the detection unit 132 detects walking periods such as early stance, mid stance, end stance, early swing, early swing, mid swing, and end swing from the walking waveform based on the detected walking events.

For example, the detection unit 132 detects walking periods and walking events from the walking waveform based on the percentage of the walking phase. If the same person is walking under the same conditions, the timing at which walking periods and walking events are detected is almost constant. Even if the person is different, the timing at which walking periods and walking events are detected shows the same tendency. Therefore, walking periods and walking events can be identified based on the percentage of the walking phase.

For example, the detection unit 132 may detect walking periods and walking events based on features extracted from the walking waveform. For example, the detection unit 132 detects the timing at which the walking waveform of the plantar angle becomes minimum as the timing of the start of the stance phase. For example, the detection unit 132 detects the timing at which the walking waveform of the plantar angle becomes maximum as the timing of the start of the swing phase. For example, the detection unit 132 detects the timing of the midpoint between the start of the stance phase and the start of the swing phase as the timing of heel lift.

For example, the detection unit 132 detects a walking event based on a walking waveform starting from the timing of heel lift. The detection unit 132 detects the timing at which a valley appears between two peaks included in the maximum peak in the walking waveform of the forward acceleration (Y-direction acceleration) as the timing of toe-off. For example, the detection unit 132 detects the minimum peak at about 60% of the walking cycle in the walking waveform of the forward acceleration (Y-direction acceleration) as the timing of sudden deceleration of the foot at the end of the swing phase. For example, the detection unit 132 detects the maximum peak at about 70% of the walking cycle in the walking waveform of the forward acceleration (Y-direction acceleration) as the timing of heel rocker. For example, the detection unit 132 detects the midpoint between the minimum peak and the maximum peak in the walking waveform of the forward acceleration (Y-direction acceleration) as the timing of heel contact. For example, the detection unit 132 detects the timing of the maximum peak between the toe-off and the heel-on-ground in the walking waveform of the vertical acceleration (Z-direction acceleration) as the timing of the tibia vertical. For example, the detection unit 132 detects the timing of a gentle maximum peak between the toe-off and the tibia vertical in the walking waveform of the forward acceleration (Y-direction acceleration) as the timing of the foot crossing. For example, the detection unit 132 detects the timing of the opposite foot heel-on-ground and the opposite foot toe-off from the walking waveform of the roll angular velocity. For example, the detection unit 132 detects the timing of the acceleration inflection point in the curve from the starting point to the toe-off timing in the walking waveform of the roll angular velocity as the timing of the opposite foot heel-on-ground. For example, the detection unit 132 detects the timing of the deceleration inflection point in the curve from the heel-on-ground timing to the end point in the walking waveform of the roll angular velocity as the timing of the opposite foot toe-off.

The gait measurement unit 133 acquires information on the walking period and walking events detected by the detection unit 132. The gait measurement unit 133 performs measurements related to the gait using the information acquired from the detection unit 132. For example, the gait measurement unit 133 measures the user's gait based on the walking events detected from the walking waveform. For example, the gait measurement unit 133 measures gait such as stride length, step length, stride width, foot angle, and walking speed based on the detected walking events. For example, the gait measurement unit 133 may estimate physical conditions such as the degree of pronation/supination, the progress of hallux valgus, body symmetry, and body flexibility based on the measured gait. For example, the gait measurement unit 133 may estimate physical conditions such as muscle weakness, bone density, and basal metabolism based on the measured gait. For example, the gait measurement unit 133 may measure body parameters such as the lengths of the upper limbs, lower limbs, upper arms, forearms, upper legs, and lower legs based on the measured gait. There are no particular limitations on the items to be measured by the gait measurement unit 133.

The gait measurement device 13 outputs the results (also referred to as gait information) measured by the gait measurement unit 133. For example, the gait measurement device 13 outputs the gait information to a display device (not shown) or a mobile terminal (not shown). The gait information output to the display device is displayed on the screen of the display device or the mobile terminal. For example, the gait measurement device 13 outputs the gait information to an external system (not shown). The gait information output from the gait measurement device 13 can be used for any purpose. There are no particular limitations on the communication function through which the gait measurement device 13 outputs the gait information.

(Operation)
Next, the operation of the interpolation device 12 of the gait measurement system 1 will be described with reference to the drawings. Descriptions of the operations of the measurement device 11 and the gait measurement device 13 will be omitted. Below, the processes performed by the gait information processing unit 122, the missing information processing unit 123, and the interpolation unit 126 included in the interpolation device 12 will be described individually. The following operation of the interpolation device 12 may include processes and sequences different from those of the interpolation device 12 described above.

[Gait Information Processing]
First, the gait information processing by the gait information processing unit 122 will be described with reference to a flowchart. Fig. 13 is a flowchart for explaining the gait information processing by the gait information processing unit 122. In explaining the processing according to the flowchart of Fig. 13, the gait information processing unit 122 will be described as the subject of action.

In FIG. 13, first, the gait information processing unit 122 acquires time series data of sensor data (step S111).

If there is a missing part in the time series data (Yes in step S112), the gait information processing unit 122 outputs the time series data including the missing part to the missing part information processing unit 123 (step S113). The gait information processing unit 122 may store the time series data including the missing part in the storage unit 125. After step S113, the process proceeds to step S118.

On the other hand, if there is no missing data in the time series data (No in step S112), the gait information processing unit 122 detects walking events from the acquired time series data (step S114). For example, the gait information processing unit 122 detects walking events such as heel contact, toe lift, and heel lift from the walking waveform.

After step S114, the gait information processing unit 122 extracts a gait waveform for one step cycle based on the detected walking event (step S115). For example, the gait information processing unit 122 extracts a gait waveform for one step cycle starting from heel contact. For example, the gait information processing unit 122 extracts a gait waveform for one step cycle starting from toe off.

Next, the gait information processing unit 122 normalizes the extracted walking waveform for one cycle (step S116). For example, the gait information processing unit 122 normalizes the walking phase and amplitude of the walking waveform.

Next, the gait information processing unit 122 stores the normalized gait waveform in the memory unit 125 (step S117). The gait waveform stored in the memory unit 125 is used to interpolate missing sections included in the missing waveform and for gait measurement by the gait measurement device 13.

If the process is to be continued (Yes in step S118), the process returns to step S111. If the process is not to be continued (No in step S118), the process according to the flowchart in FIG. 13 ends. The conditions for determining whether to continue the process in step S118 may be set in advance.

[Missing information processing]
Next, the missing information processing by the missing information processing unit 123 will be described with reference to a flowchart. Fig. 14 is a flowchart for explaining the missing information processing by the missing information processing unit 123. In the explanation of the processing according to the flowchart of Fig. 14, the missing information processing unit 123 will be described as the subject of operation.

14, first, the missing information processing unit 123 acquires time series data including missing parts (missing waveform) from the gait information processing unit 122 (step S121). The missing information processing unit 123 may acquire the missing waveform from the memory unit 125.

Next, the missing information processing unit 123 identifies missing sections contained in the acquired missing waveform based on the timestamp (step S122).

Next, the missing information processing unit 123 calculates the walking phase of the identified missing section (step S123).

Next, the missing information processing unit 123 stores information (missing information) about the walking phase of the missing section included in the missing waveform in the storage unit 125 (step S124). The missing information stored in the storage unit 125 is used by the interpolation unit 126 to interpolate the missing section.

[Interpolation Processing]
Next, the interpolation process by the interpolation unit 126 will be described with reference to a flowchart. Here, an example in which interpolation data is generated in all sections (FIG. 15) and an example in which interpolation is performed in some sections using an analytical method (FIG. 16) will be described.

Figure 15 is a flowchart for explaining the interpolation process of the interpolation unit 126 when generating interpolation data for all sections. In the explanation following the flowchart of Figure 15, the interpolation unit 126 will be described as the subject of operation.

15, first, the interpolation unit 126 acquires time series data including a missing section (missing waveform) from the storage unit 125 (step S131). The interpolation unit 126 may acquire the missing waveform from the gait information processing unit 122. The missing waveform is associated with missing information indicating the walking phase of the missing section.

Next, the interpolation unit 126 acquires from the memory unit 125 a walking waveform of another walking cycle in which there is no missing walking phase in the missing section (step S132).

Next, the interpolation unit 126 uses the acquired walking waveform data to generate interpolation data for the missing section (step S133).

Next, the interpolation unit 126 corrects the start and end points of the interpolated data and inserts the interpolated data into the missing section (step S134).

Next, the interpolation unit 126 resamples the corrected waveform to return it to time series data (step S135). Step S135 is performed because the original time series data is required when calculating walking speed, stride length, etc. If the original time series data is not required, step S135 may be omitted.

Figure 16 is a flowchart for explaining the interpolation process of the interpolation unit 126 when an analytical method is used to interpolate in some sections. In the explanation following the flowchart of Figure 16, the interpolation unit 126 will be described as the subject of operation.

16, first, the interpolation unit 126 acquires time series data including a missing section (missing waveform) from the storage unit 125 (step S141). The interpolation unit 126 may acquire the missing waveform from the gait information processing unit 122. The missing waveform is associated with missing information indicating the walking phase of the missing section.

If the missing section is one for which an analytical method can be used (Yes in step S142), the interpolation unit 126 interpolates the data of the missing section using an analytical method (step S143). After step S143, the process proceeds to step S147.

On the other hand, if the missing section is not one for which analytical methods can be used (No in step S142), the interpolation unit 126 acquires from the memory unit 125 a walking waveform of another walking cycle in which there is no missing part in the walking phase of the missing section (step S144).

Next, the interpolation unit 126 uses the acquired walking waveform data to generate interpolation data for the missing section (step S145).

Next, the interpolation unit 126 corrects the start and end points of the interpolated data and inserts the interpolated data into the missing section (step S146).

Next, the interpolation unit 126 resamples the corrected waveform to return it to time series data (step S146). Step S146 is performed because the original time series data is required when calculating walking speed, stride length, etc. If the original time series data is not required, step S146 may be omitted.

As described above, the gait measurement system of this embodiment includes a measurement device, an interpolation device, and a gait measurement device. The measurement device is placed on a user's footwear. The measurement device measures spatial acceleration and spatial angular velocity according to the user's gait. The measurement device generates sensor data based on the measured spatial acceleration and spatial angular velocity. The measurement device outputs the generated sensor data to the interpolation device. The interpolation device has a receiving unit, a gait information processing unit, a missing information processing unit, a storage unit, an interpolation unit, and a transmission unit. The receiving unit receives the sensor data transmitted from the measurement device. The gait information processing unit generates time-series data of the sensor data. The gait information processing unit generates a gait waveform for each gait cycle using the time-series data of the sensor data related to the movement of the feet, and identifies a missing section of data in the time-series data. The gait information processing unit stores the generated gait waveform and information on the identified missing section in the storage unit. The storage unit stores the gait waveform, information on the missing section, and a repair waveform in which the missing section is interpolated. The missing information processing unit calculates the gait phase of the identified missing section. The interpolation unit generates interpolation data for interpolating the missing section by using data of a walking phase of the missing section in a walking waveform having a walking cycle different from the walking cycle including the missing section. The interpolation unit interpolates the missing section with the generated interpolation data.
The gait measurement device acquires from the interpolation device a gait waveform that does not include a missing section that is generated by the interpolation device using time-series data of the sensor data, and a gait waveform in which the interpolation device interpolates data of the missing section. The gait measurement device measures the user's gait based on walking events detected from the acquired gait waveform. The gait measurement device outputs information related to the measured gait of the user.

In the method of this embodiment, by focusing on the periodicity of walking, interpolation data is generated to fill in missing sections of data that occur in the time series data of sensor data measured in response to the user's walking. In the method of this embodiment, interpolation data is generated using data from the same walking phase of walking waveforms with different walking cycles. Therefore, according to the method of this embodiment, since interpolation data generated by focusing on the periodicity of walking is used, data of missing sections can be interpolated, including the characteristics of the missing sections of data contained in the time series data of sensor data.

When communicating sensor data measured by a wearable sensor with wireless communication capabilities, data loss may occur due to communication failure. Data loss due to communication failure is often continuous, not discrete. For example, important data used for feature extraction may be lost entirely from time-series sensor data. According to the method of this embodiment, the similarity and periodicity of walking movements are used to interpolate data loss intervals, so that data loss intervals spanning several percent to several tens of percent of the walking phase can be interpolated. In addition, the method of this embodiment can also be used to remove outliers measured due to circuitry-related factors and to smooth out abnormal values measured due to unknown factors.

In one aspect of this embodiment, the gait information processing unit extracts a waveform for one step walking cycle from the time series data. The gait information processing unit normalizes the walking phase included in the extracted waveform to generate a walking waveform. According to this aspect, the walking phases of multiple walking waveforms generated from the time series data of the sensor data are unified, making it easier to mutually interpolate data between the multiple walking waveforms.

In one aspect of this embodiment, the interpolation unit selects, for a missing section included in the time series data, at least one piece of data for the walking phase included in the missing section from at least one walking waveform in which data for the walking phase included in the missing section is not missing. The interpolation unit generates interpolated data using the data for the selected walking phase. According to this aspect, the missing section can be interpolated using data for other walking cycles.

In one aspect of this embodiment, the interpolation unit calculates the average value of data for a walking phase selected from walking waveforms of multiple walking cycles. The interpolation unit generates interpolated data using the average value of the calculated walking phase data. According to this aspect, data for missing sections is interpolated based on the average value of data for multiple walking cycles, so that interpolated data that better reflects the characteristics of walking can be generated.

In one aspect of this embodiment, the interpolation unit generates interpolation data using an analytical method for walking periods with small data fluctuations. For walking periods with large data fluctuations, the interpolation unit generates interpolation data using data from a walking cycle that is different from the walking cycle that includes the missing section. According to this aspect, for walking periods with small data fluctuations, the interpolation data is generated using an analytical method, which reduces the calculation time and amount of calculations.

Second Embodiment
Next, a gait measurement system according to a second embodiment will be described with reference to the drawings. The gait measurement system of this embodiment differs from the first embodiment in that it generates interpolation data for missing sections based on the deviation value in the overall distribution of data values (amplitude values) for each walking phase related to the walking waveform of a plurality of walking cycles.

(composition)
17 is a block diagram showing the configuration of a gait measurement system 2 of this embodiment. The gait measurement system 2 includes a measurement device 21, an interpolation device 22, and a gait measurement device 23. The interpolation device 22 may be connected to the measurement device 21 and the gait measurement device 23 by wire or wirelessly. The measurement device 21, the interpolation device 22, and the gait measurement device 23 may be configured as a single device. The gait measurement system 2 may be configured from the interpolation device 22 and the gait measurement device 23, excluding the measurement device 21.

The measuring device 21 has the same configuration as the measuring device 11 of the first embodiment. The measuring device 21 is installed on the foot. The measuring device 21 measures acceleration (also called spatial acceleration) measured by an acceleration sensor and angular velocity (also called spatial angular velocity) measured by an angular velocity sensor as physical quantities related to the movement of the foot of a user wearing the footwear. The physical quantities related to the movement of the foot measured by the measuring device 21 also include velocity, angle, and position (trajectory) calculated by integrating the acceleration and angular velocity. The measuring device 21 converts the measured physical quantities into digital data (also called sensor data). The measuring device 21 transmits the converted sensor data to the interpolation device 22.

The interpolation device 22 receives sensor data from the measurement device 21. The interpolation device 22 generates time series data of the received sensor data. The interpolation device 22 generates the time series data based on the timestamp included in the sensor data. The interpolation device 22 extracts a waveform for one step walking cycle from the generated time series data. For example, the interpolation device 22 extracts a waveform for one step walking cycle starting from the timing of heel strike or heel lift. The interpolation device 22 normalizes the extracted waveform for one step walking cycle to generate a waveform for one step walking cycle (also called a walking waveform).

The interpolation device 22 identifies a portion of the time series data of the sensor data where the number of the time stamp is missing as a missing section. The interpolation device 22 generates interpolation data for interpolating the data of the missing section based on the overall distribution of the data values of the walking phase included in the missing section. The overall distribution is the distribution of the data values for each walking phase included in the missing section, with the walking waveforms of the multiple walking cycles used to interpolate the missing section as the whole. In other words, the interpolation device 22 calculates the statistics in the overall distribution of the data values of the walking phase corresponding to the missing section using the data values (amplitude values) of the walking waveforms of the multiple walking cycles in which the walking phase of the missing section has no missing data. The interpolation device 22 generates the interpolation data for the missing section based on the statistics in the overall distribution of the data values for each walking phase included in the missing section. In particular, the interpolation device 22 generates the interpolation data for the missing section based on a representative value in the overall distribution of the data values for each walking phase included in the missing section. For example, the interpolation device 22 generates the interpolation data for the missing section based on the deviation value in the overall distribution of the data values (amplitude values) for each walking phase included in the missing section. For example, the interpolation device 22 may generate the interpolation data for the missing section based on the standard deviation, variance, deviation, etc. instead of the deviation value. The interpolation device 22 uses the generated interpolation data to interpolate the missing section.

The gait measurement device 23 has the same configuration as the gait measurement device 13 of the first embodiment. The gait measurement device 23 acquires a gait waveform that does not include a missing section from the interpolation device 22. The gait measurement device 23 performs measurements related to gait using the acquired gait waveform. The gait measurement device 23 outputs measurement results related to gait (also called gait information).

For example, the interpolation device 22 and the gait measurement device 23 are implemented in a server or the like (not shown). For example, the interpolation device 22 and the gait measurement device 23 may be realized by an application server. For example, the interpolation device 22 and the gait measurement device 23 may be realized by application software or the like installed on a mobile terminal (not shown).

[Interpolation device]
Next, a detailed configuration of the interpolation device 22 will be described with reference to the drawings. Fig. 18 is a block diagram showing an example of the detailed configuration of the interpolation device 22. The interpolation device 22 includes a receiving unit 221, a gait information processing unit 222, a missing information processing unit 223, a storage unit 225, an interpolation unit 226, and a transmitting unit 228.

The receiving unit 221 has a configuration similar to that of the receiving unit 121 of the first embodiment. The receiving unit 221 receives sensor data from a measuring device (not shown). The receiving unit 221 outputs the received sensor data to the gait information processing unit 222.

The gait information processing unit 222 has a configuration similar to that of the gait information processing unit 122 of the first embodiment. The gait information processing unit 222 acquires sensor data from the receiving unit 221. The gait information processing unit 222 generates time series data of the acquired sensor data. The gait information processing unit 222 generates the time series data based on a timestamp included in the sensor data. The gait information processing unit 222 extracts a waveform for one step gait cycle from the generated time series data. The gait information processing unit 222 normalizes the extracted waveform for one step gait cycle to generate a gait waveform for one step gait cycle. The gait information processing unit 222 stores the normalized gait waveform in the memory unit 225.

The missing information processing unit 223 has a configuration similar to that of the missing information processing unit 123 of the first embodiment. The missing information processing unit 223 acquires a missing waveform. The missing information processing unit 223 stores information about a missing section included in the missing waveform (also called missing information) in the memory unit 225 in association with the missing waveform.

The memory unit 225 has the same configuration as the memory unit 125 of the first embodiment. A gait waveform is stored in the memory unit 225. The gait waveforms stored in the memory unit 225 include a gait waveform that does not include a missing section (also called a normal waveform), a gait waveform that includes a missing section (also called a missing waveform), and a gait waveform in which the missing section has been repaired (also called a repaired waveform). The missing waveform is associated with the missing information of the missing waveform. The gait waveform stored in the memory unit 225 is acquired by the transmission unit 228 at a predetermined timing and transmitted from the transmission unit 228 to a gait measurement device (not shown).

The interpolation unit 226 acquires from the storage unit 225 a plurality of walking waveforms having no missing parts in the walking phase of the missing section included in the missing waveform to be interpolated. The interpolation unit 226 uses the data values (amplitude values) of the acquired plurality of walking waveforms to calculate statistics in the overall distribution of the data values of the walking phase corresponding to the missing section in the data group of the plurality of walking waveforms. In particular, the interpolation unit 226 calculates representative values such as deviation values, standard deviations, variances, and deviations as statistics. For example, the interpolation unit 226 calculates the deviation values of the data values of the walking phase included in the missing section in the overall distribution of the data group of the plurality of walking waveforms. The interpolation unit 226 generates the interpolation data based on the calculated statistics. For example, the interpolation unit 226 generates the interpolation data based on the deviation values. For example, the interpolation unit 226 may generate the interpolation data of the missing section based on the standard deviation, variance, deviation, etc. instead of the deviation values. The interpolation unit 226 uses the generated interpolation data to interpolate the missing section.

Here, a method for generating interpolated data based on a deviation value, which is one of the statistics (representative values), will be explained using several drawings (Figs. 19 to 23). Fig. 19 shows time series data of forward acceleration (Y-direction acceleration) measured as the user walks. The time series data in Fig. 19 includes waveforms of multiple walking cycles over a measurement period of 20 seconds. The waveforms of each walking cycle show a similar pattern, although there are differences in the data values (amplitude values).

Figure 20 shows a waveform (walking waveform) obtained by extracting one of the multiple walking cycle waveforms contained in the time series data of Figure 19 and normalizing the extracted waveform. The walking waveform of Figure 20 shows a pattern that includes walking characteristics. Figure 20 shows walking phases (P1, P2) that will be used in the following explanation. In the following, walking phase P1 and walking phase P2 apply not only to the walking cycle of Figure 20 but also to multiple walking cycles.

Figure 21 shows the frequency distribution of data values (amplitude values) in walking phases P1 and P2, with the walking waveforms of multiple walking cycles extracted from the time series data of Figure 19 as the sample group (whole). For walking phase P1, the frequency distribution of data values shows a distribution close to a normal distribution. For walking phase P2, the frequency distribution of data values shows a distribution close to a normal distribution. For all other walking phases, the frequency distribution of data values for each 1% was normalized and judged using the Kolmogorov-Smirnov test, and a positive result was obtained. In other words, the frequency distribution of data values in each walking phase of the walking waveforms of multiple walking cycles shows a distribution close to a normal distribution regardless of the walking cycle. This shows that it is possible to estimate interpolated data for walking waveforms of multiple walking cycles based on the overall distribution of data values for each walking phase. In other words, it is possible to estimate interpolated data for walking waveforms of multiple walking cycles based on statistics in the overall distribution of data values for each walking phase.

Figure 22 is a graph showing the correlation between the standard deviations in the overall distribution of data values of data N and data N+1 in consecutive walking phases in the time series data of the sensor data in Figure 19 (N is a natural number). As shown in Figure 22, the standard deviations of consecutive data N and data N+1 show an almost proportional relationship. In other words, the standard deviations in the overall distribution of data values in walking phase P2 show similar values for consecutive data N and data N+1.

23 is a graph showing the correlation coefficient of the deviation value according to the distance from the target walking phase (walking phase P2). The solid line in FIG. 23 shows the correlation coefficient between the deviation value of the data value of walking phase P2 and the data value of a walking phase different from walking phase P2 for the sample group of walking waveforms of multiple walking cycles cut out from the time series data in FIG. 19. The dashed line in FIG. 23 is a curve obtained by fitting the correlation coefficient (solid line) to a polynomial. As shown in FIG. 23, it can be seen that the closer the walking phase is from the target walking phase, the larger the correlation coefficient of the deviation value and the more similar the deviation value is. In other words, the closer the walking phase is from the target walking phase, the larger the correlation coefficient and the closer the deviation value is. In other words, the data value of a walking phase with a deviation value close to the deviation value of the target walking phase can be used to generate interpolated data for the target walking phase.

For example, the interpolation unit 226 calculates the interpolation data by performing a reverse calculation from the deviation value of the calculated walking phase, and generates the interpolation data for interpolating the missing section. For example, the interpolation unit 226 may generate the interpolation data based on a representative value such as a standard deviation, a variance, or a deviation, instead of the deviation value. For example, the interpolation unit 226 calculates the value d _j of the interpolation data in the walking phase j by performing a reverse calculation of the following formula 1. The following formula 1 is a calculation formula for the deviation value T _j of the data value of the walking phase j included in the missing section.

In the above formula 1, μ is the average value of the data values of walking phase j in the multiple walking waveforms included in the target data group. σ is the standard deviation of the data values of walking phase j in the multiple walking waveforms included in the target data group. When generating interpolated data based on representative values such as standard deviation, variance, and deviation instead of deviation values, the value of the interpolated data can be calculated by inversely calculating the formula for standard deviation, variance, and deviation.

For example, the interpolation unit 226 may estimate the interpolation data of the missing section based on the deviation value of the data value of the start point and the end point of the missing section included in the missing waveform to be interpolated. FIG. 24 is a graph for explaining an example of the interpolation of the missing section based on the deviation value of the start point (walking phase M1) and the end point (walking phase M2) of the missing section included in the missing waveform to be interpolated. For example, the interpolation unit 226 calculates the average value of the deviation value in the entire distribution of the data value of the walking phase M1 and the deviation value in the entire distribution of the data value of the walking phase M2 for the missing section. The interpolation unit 226 estimates the interpolation data from the entire distribution of the data value using the average value of the deviation values of the data values of the walking phase M1 and the walking phase M2. In the method of FIG. 24, the closer the distance between the walking phase M1 and the walking phase M2 of the missing section, the higher the estimation accuracy of the interpolation data.

For example, the method of generating interpolated data by the interpolation unit 226 of this embodiment may be combined with the method of generating interpolated data by the interpolation unit 126 of the first embodiment. For example, interpolated data may be generated by the method of the first embodiment, and the start point and end point of the generated interpolated data may be corrected by the method of this embodiment.

The interpolation unit 226 stores the walking waveform (repaired waveform) in which the missing sections have been interpolated in the memory unit 225. For example, the interpolation unit 226 may label the missing sections in the repaired waveform so that the repaired missing sections can be identified. For example, the interpolation unit 226 may store in the memory unit 225 a repaired waveform (also called a provisional repaired waveform) in which provisional interpolation data has been inserted into the missing sections. The repaired waveform stored in the memory unit 225 is used for gait measurement by a gait measurement device (not shown) in the same way as other walking waveforms.

The transmission unit 228 acquires a gait waveform from the memory unit 225. The transmission unit 228 acquires a gait waveform including a normal waveform and a restored waveform from the memory unit 225. The transmission unit 228 transmits the acquired gait waveform to a gait measurement device (not shown). The transmission unit 228 may transmit the gait waveform to the gait measurement device via a wired connection such as a cable, or may transmit the gait waveform to the gait measurement device via wireless communication. There are no particular limitations on the communication method between the transmission unit 228 and the gait measurement device.

(Operation)
Next, the operation of the interpolation device 22 will be described with reference to the drawings. In the following, an example will be described in which the interpolation unit 226 included in the interpolation device 22 performs interpolation of a missing section based on the deviation values of the start point and end point of the missing section. The following operation of the interpolation device 22 may include processing and an order different from those of the above-mentioned interpolation unit 226. The processing of the gait information processing unit 222 and the missing information processing unit 223 is omitted since it is the same as in the first embodiment.

[Interpolation Processing]
The interpolation process by the interpolation unit 226 will be described with reference to a flowchart. Fig. 25 is a flowchart for explaining the interpolation process by the interpolation unit 226. In the explanation based on the flowchart of Fig. 25, the interpolation unit 226 will be described as the subject of operation.

25, first, the interpolation unit 226 acquires time series data including a missing section (missing waveform) from the storage unit 225 (step S231). The interpolation unit 226 may acquire the missing waveform from the gait information processing unit 222. The missing waveform is associated with missing information indicating the walking phase of the missing section.

Next, the interpolation unit 226 acquires from the memory unit 225 walking waveforms of multiple walking cycles in which the walking phase of the missing section included in the missing waveform is not missing (step S232).

Next, the interpolation unit 226 uses the acquired data of multiple walking waveforms to derive the overall distribution of data for the walking phase corresponding to the missing section (step S233).

Next, the interpolation unit 226 calculates the standard deviation of the walking phase at the start and end of the missing section in the overall distribution of data values of the walking phase included in the missing section (step S234).

Next, the interpolation unit 226 uses the calculated deviation value to generate interpolation data for the missing section (step S235).

Next, the interpolation unit 226 inserts the generated interpolation data into the missing section (step S236). For example, the interpolation unit 226 corrects the start point and end point of the interpolation data and inserts the interpolation data into the missing section.

Next, the interpolation unit 226 resamples the corrected waveform to return it to time series data (step S237). Step S237 is performed because the original time series data is required when calculating walking speed, stride length, etc. If the original time series data is not required, step S237 may be omitted.

As described above, the gait measurement system of this embodiment includes a measurement device, an interpolation device, and a gait measurement device. The measurement device is placed on the user's footwear. The measurement device measures spatial acceleration and spatial angular velocity according to the user's gait. The measurement device generates sensor data based on the measured spatial acceleration and spatial angular velocity. The measurement device outputs the generated sensor data to the interpolation device. The interpolation device has a receiving unit, a gait information processing unit, a missing information processing unit, a storage unit, an interpolation unit, and a transmission unit. The receiving unit receives the sensor data transmitted from the measurement device. The gait information processing unit generates time-series data of the sensor data. The gait information processing unit generates a gait waveform for each gait cycle using the time-series data of the sensor data related to the movement of the foot, and identifies a missing section of data in the time-series data. The gait information processing unit stores information about the generated gait waveform and the identified missing section in the storage unit. The storage unit stores the gait waveform, information about the missing section, and a repair waveform in which the missing section is interpolated. The missing information processing unit calculates the gait phase of the identified missing section. The interpolation unit generates interpolation data for the missing section based on a representative value of data for each walking phase included in the missing section in a data group of walking waveforms of multiple walking cycles used for interpolating the missing section. For example, the interpolation unit generates the interpolation data for the missing section using a deviation value of data for each walking phase included in the missing section. The interpolation unit interpolates the generated interpolation data into the missing section. The gait measurement device acquires from the interpolation device a gait waveform that does not include the missing section generated by the interpolation device using time-series data of the sensor data, and a gait waveform in which the interpolation device has interpolated data for the missing section. The gait measurement device measures the user's gait based on walking events detected from the acquired gait waveform. The gait measurement device outputs information related to the measured gait of the user.

In the method of this embodiment, attention is focused on the periodicity of walking, and interpolation data is generated to fill in missing sections of data that occur in time-series data of sensor data measured in response to the user's walking. In the method of this embodiment, interpolation data is generated based on a representative value of data for each walking phase included in the missing section. In the method of this embodiment, interpolation data is generated based on the distribution of walking waveform data for multiple walking cycles generated from the time-series data. According to the method of this embodiment, by generating interpolation data based on the overall distribution, walking waveform data including sudden abnormalities is smoothed, so that data in the missing section can be restored with higher accuracy.

Third Embodiment
Next, an interpolation device according to a third embodiment will be described with reference to the drawings. The interpolation device of this embodiment has a simplified configuration of the interpolation devices of the first and second embodiments. Fig. 26 is a block diagram showing an example of the configuration of an interpolation device 32 of this embodiment. The interpolation device 32 includes a gait information processing unit 322, a missing information processing unit 323, and an interpolation unit 326.

The gait information processing unit 322 generates a walking waveform for each walking cycle using time series data of sensor data related to foot movement, and identifies missing sections of data in the time series data. The missing information processing unit 323 calculates the walking phase of the identified missing section. The interpolation unit 326 generates interpolation data that interpolates the missing section using data on the walking phase of the missing section in a walking waveform of a walking cycle different from the walking cycle that includes the missing section. The interpolation unit 326 interpolates the generated interpolation data into the missing section.

According to this embodiment, interpolated data generated with a focus on the periodicity of walking is used, so that data for missing sections can be interpolated, including the characteristics of the missing sections of data contained in the time series data of the sensor data.

(Hardware)
Here, a hardware configuration for executing the control and processing according to each embodiment of the present disclosure will be described using an information processing device 90 in Fig. 27 as an example. Note that the information processing device 90 in Fig. 27 is an example configuration for executing the control and processing according to each embodiment, and does not limit the scope of the present disclosure.

As shown in FIG. 27, the information processing device 90 includes a processor 91, a main memory device 92, an auxiliary memory device 93, an input/output interface 95, and a communication interface 96. In FIG. 27, the interface is abbreviated as I/F (Interface). The processor 91, the main memory device 92, the auxiliary memory device 93, the input/output interface 95, and the communication interface 96 are connected to each other via a bus 98 so as to be able to communicate data with each other. In addition, the processor 91, the main memory device 92, the auxiliary memory device 93, and the input/output interface 95 are connected to a network such as the Internet or an intranet via the communication interface 96.

The processor 91 expands a program stored in the auxiliary storage device 93 or the like into the main storage device 92. The processor 91 executes the program expanded into the main storage device 92. In this embodiment, a configuration may be used in which a software program installed in the information processing device 90 is used. The processor 91 executes the control and processing related to this embodiment.

The main memory 92 has an area in which programs are expanded. Programs stored in the auxiliary memory 93 or the like are expanded in the main memory 92 by the processor 91. The main memory 92 is realized by a volatile memory such as a DRAM (Dynamic Random Access Memory). In addition, a non-volatile memory such as an MRAM (Magnetoresistive Random Access Memory) may be configured/added to the main memory 92.

The auxiliary storage device 93 stores various data such as programs. The auxiliary storage device 93 is realized by a local disk such as a hard disk or flash memory. Note that it is also possible to configure the main storage device 92 to store various data and omit the auxiliary storage device 93.

The input/output interface 95 is an interface for connecting the information processing device 90 to peripheral devices based on standards and specifications. The communication interface 96 is an interface for connecting to external systems and devices through a network such as the Internet or an intranet based on standards and specifications. The input/output interface 95 and the communication interface 96 may be a common interface for connecting to external devices.

If necessary, input devices such as a keyboard, mouse, or touch panel may be connected to the information processing device 90. These input devices are used to input information and settings. When a touch panel is used as an input device, the display screen of the display device may also serve as an interface for the input device. Data communication between the processor 91 and the input devices may be mediated by the input/output interface 95.

The information processing device 90 may also be equipped with a display device for displaying information. When a display device is equipped, it is preferable that the information processing device 90 is equipped with a display control device (not shown) for controlling the display of the display device. The display device may be connected to the information processing device 90 via the input/output interface 95.

The information processing device 90 may also be equipped with a drive device. The drive device mediates between the processor 91 and a recording medium (program recording medium), reading data and programs from the recording medium, writing the processing results of the information processing device 90 to the recording medium, and the like. The drive device may be connected to the information processing device 90 via the input/output interface 95.

The above is an example of a hardware configuration for enabling the control and processing according to each embodiment of the present invention. The hardware configuration in FIG. 27 is an example of a hardware configuration for executing the control and processing according to each embodiment, and does not limit the scope of the present invention. In addition, a program that causes a computer to execute the control and processing according to each embodiment is also included in the scope of the present invention. Furthermore, a program recording medium on which a program according to each embodiment is recorded is also included in the scope of the present invention. The recording medium can be realized, for example, by an optical recording medium such as a CD (Compact Disc) or a DVD (Digital Versatile Disc). The recording medium may be realized by a semiconductor recording medium such as a USB (Universal Serial Bus) memory or an SD (Secure Digital) card. The recording medium may also be realized by a magnetic recording medium such as a flexible disk or other recording medium. When a program executed by a processor is recorded on a recording medium, the recording medium corresponds to a program recording medium.

The components of each embodiment may be combined in any manner. The components of each embodiment may be realized by software or by circuitry.

Although the present invention has been described above with reference to the embodiments, the present invention is not limited to the above-mentioned embodiments. Various modifications that can be understood by a person skilled in the art can be made to the configuration and details of the present invention within the scope of the present invention.

REFERENCE SIGNS LIST 1, 2 Gait measurement system 11, 21 Measurement device 12, 22, 32 Interpolation device 13, 23 Gait measurement device 111 Acceleration sensor 112 Angular velocity sensor 113 Control unit 115 Transmission unit 121, 221 Reception unit 122, 222, 322 Gait information processing unit 123, 223, 323 Missing information processing unit 125, 225 Storage unit 126, 226, 326 Interpolation unit 128, 228 Transmission unit 131 Acquisition unit 132 Detection unit 133 Gait measurement unit

Claims (9)

a gait information processing means for generating a gait waveform for each gait cycle using time series data of the sensor data relating to foot movement and for identifying a data missing section in the time series data;
A missing information processing means for calculating a walking phase of the identified missing section;
an interpolation means for generating interpolation data for interpolating the missing section using data of the walking phase of the missing section in a walking waveform having a walking cycle different from a walking cycle including the missing section, and for interpolating the generated interpolation data into the missing section ;
The interpolation means
With respect to the missing section included in the time series data, at least one piece of data of the walking phase included in the missing section is selected from at least one of the walking waveforms in which data of the walking phase included in the missing section is not missing;
An interpolation device that generates the interpolated data using data of the selected walking phase . The walking information processing means includes:
A waveform for one walking cycle is extracted from the time series data,
The interpolation device according to claim 1 , wherein the walking waveform is generated by normalizing the walking phase included in the extracted waveform. The interpolation means
Calculating an average value of data of the walking phase selected from the walking waveforms of the plurality of walking cycles;
3. The interpolation device according to claim 1, wherein the interpolated data is generated using an average value of the calculated data of the walking phase. The interpolation means
For a walking period included in the stance phase in which data fluctuation is smaller than that of the swing phase , the interpolated data is generated using an analytical method;
4. The interpolation device according to claim 1, wherein, for a walking period included in the swing phase in which data fluctuation is larger than that of the stance phase, the interpolated data is generated using data of a walking cycle different from the walking cycle including the missing section. The interpolation means
5. The interpolation device according to claim 1, wherein the interpolation data for the missing section is generated based on a representative value of data for each of the walking phases included in the missing section in a data group of the walking waveform for a plurality of the walking cycles used for interpolating the missing section. The interpolation means
The interpolation device according to claim 5 , wherein the interpolation data for the missing section is generated using a deviation value of data for each of the walking phases included in the missing section. An interpolation device according to any one of claims 1 to 6 ,
a measurement device that is arranged in a user's footwear, measures spatial acceleration and spatial angular velocity in response to the user's walking, generates sensor data based on the measured spatial acceleration and spatial angular velocity, and outputs the generated sensor data to the interpolation device;
a gait measurement device that acquires, from the interpolation device, a gait waveform that does not include missing sections that is generated by the interpolation device using time-series data of the sensor data and a gait waveform in which the interpolation device interpolates data of the missing sections, measures a gait of the user based on walking events detected from the acquired gait waveform, and outputs information regarding the measured gait of the user. The computer
A walking waveform is generated for each walking cycle using time series data of the sensor data regarding the movement of the feet.
Identifying a data missing section in the time series data;
Calculate the walking phase of the identified missing section;
generating interpolation data for interpolating the missing section using data of the walking phase of the missing section in a walking waveform having a walking cycle different from the walking cycle including the missing section;
The generated interpolation data is interpolated into the missing section ;
In the interpolation,
With respect to the missing section included in the time series data, at least one piece of data of the walking phase included in the missing section is selected from at least one of the walking waveforms in which data of the walking phase included in the missing section is not missing;
An interpolation method for generating the interpolated data using data of the selected walking phase . A process of generating a walking waveform for each walking cycle using time series data of the sensor data related to foot movement;
A process of identifying a data missing section in the time series data;
A process of calculating a walking phase of the identified missing section;
A process of generating interpolation data for interpolating the missing section using data of the walking phase of the missing section in a walking waveform having a walking cycle different from a walking cycle including the missing section;
A process of interpolating the generated interpolation data into the missing section;
In the interpolation process,
selecting at least one piece of data of the walking phase included in the missing section from at least one of the walking waveforms having no missing data of the walking phase included in the missing section, for the missing section included in the time series data;
and generating the interpolated data using data of the selected walking phase .

Images